- design efficient data collection methods
- minimize costs of time/money
- maximize information
c
29 June 2016
c
Proposed in Thompson, S. (1990). Adaptive cluster sampling. Journal of the American Statistical Association, 85(412), 1050–1059.
Design:
- A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme - A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme probability sampling scheme
c
Design:
- A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme - A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme - A primary sample of \(n_1\) units
Design:
For neighboring units whose values satisfy the condition, their neighbors are also surveyed
Cluster Sampling: Sampling of neighboring units continues until no additional units satisfy the condition
- A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme - A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme
Advantages
Disadvantage
The unbiased (for ACS) Horvitz-Thompson estimator of the population mean of variable \(x\) is \(\bar{x}_{HT} = \frac{1}{N}\sum_{i=1}^{v} (x_i J_i)/\pi_i\)
Horvitz-Thompson estimators will be
We used cactus presence as our criterion to initiate cluster sampling
We ran 5000 simulations of the RACS and ACS designs per
For each simulation we estimated:
\(B_{\bar{x}_{HT,i}} = (\bar{x}_{HT,i} - \mu)/\mu\)
\(\bar{x}_{HT,i}\) Horvitz-Thompson mean of variable \(x\) from the \(i\)^th simulation
mean percent relative bias for the \(S\) simulations
\(\text{mean}(B_{\bar{x}_{HT}}) = 100 \times S^{-1} \sum_{i=1}^{S} B_{\bar{x}_{HT,i}}\)
Data Collection
- A primary sample of \(n_1\) units is selected from \(N\) units, based on some probability sampling scheme - A primary sample of \(n_1\) units is selected
Funding